Search notes

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add operational context, which it does: results are ranked by relevance, the default mode is hybrid when semantic search is available, and `lines` produces grep-like line output instead of excerpts. Pagination behavior (page/page_size) is left entirely to the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core search statement and ranking, then grouped by concern (query syntax, mode, narrowing, line output, scoping, alternative tool). Dense backtick-heavy phrasing for 22 parameters, but no sentence is redundant or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists, return values need no explanation, and the description covers the main decision points: mode selection, narrowing dimensions, and the handoff to bm_read. Only pagination and the specialist temporal/similarity parameters are unmentioned, and those are self-documented in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 95%, so the baseline is 3; the description exceeds it by explaining query syntax (quoted phrases, AND/OR/NOT, tag:name), the meaning of each mode including permalink globs, and the intent of filters/path/identifier/lines. Specialist parameters (valid_at, time_kind, valid_overlaps, min_similarity, compact, pagination) get no prose treatment, but they are documented in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Search a Basic Memory project, ranked by relevance') and immediately lists the dimensions that characterize the operation (modes, filters, line output). It routes to bm_read for full notes, so the agent can separate search from retrieval, though other similar siblings (search_notes, bm_find, grep) are never distinguished.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear when-to-use signals for each mode ('hybrid (the default when semantic search is available)', permalink 'globs with *'), says query can be omitted to search by filters alone, and points to bm_read for reading full notes. It stops short of any when-NOT-to-use guidance or comparison against the overlapping search_notes/bm_find siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.